FitMyLLM
INTEL/ Xe-HPG

Intel Data Center GPU Flex 170

16 GB
VRAM (Mid-range)
512 GB/s
Memory Bandwidth
191 / 290
Models fit at Q4 (66%)
~23 tok/s
7B Q4 speed (Good)
Model coverage at Q466% of all models

Specifications

VRAM
16 GB
Bandwidth
512 GB/s
FP16 Compute
33.6 TFLOPS
TDP
150W
Memory
GDDR6
Architecture
Xe-HPG
Compute Units
256
PCIe
Gen 4 x16
68
Fast models (>30 tok/s)
Real-time chat speed
183
Usable models (>10 tok/s)
Comfortable for all tasks
191
Total compatible
Fit in VRAM at Q4

Compatible Models(191)

S
GPT-2 124M0.124B
gpt21K ctxchat
1321
tok/s
2% VRAM
S
SmolLM2 135M0.135B
smollm2K ctxchat
1214
tok/s
2% VRAM
S
Nomic Embed Text v1.50.137B
embedding8K ctxembedding
1196
tok/s
2% VRAM
S
mxbai-embed-large-v10.335B
embedding1K ctxembedding
489
tok/s
3% VRAM
S
Snowflake Arctic Embed L0.335B
embedding1K ctxembedding
489
tok/s
3% VRAM
S
GPT-2 Medium 345M0.345B
gpt21K ctxchat
475
tok/s
3% VRAM
S
SmolLM2 360M0.36B
smollm8K ctxchat
455
tok/s
3% VRAM
S
Qwen 1.5 0.5B0.5B
qwen32K ctxchat
328
tok/s
5% VRAM
S
Qwen 2.5 0.5B0.5B
qwen32K ctxchat
328
tok/s
5% VRAM
S
BGE-M30.568B
embedding8K ctxembedding
288
tok/s
4% VRAM
S
Qwen3 0.6B0.6B
qwen32K ctxchatreasoning
273
tok/s
4% VRAM
S
GPT-2 Large 774M0.774B
gpt21K ctxchat
212
tok/s
5% VRAM
S
Qwen3-0.6B0.8B
qwen40K ctxchat
205
tok/s
6% VRAM
S
Qwen3.5-0.8B0.9B
qwen256K ctxchat
182
tok/s
6% VRAM
S
Falcon3-1B1B
falcon32K ctxchat
164
tok/s
6% VRAM
S
InternLM2 1B1B
internlm32K ctxchat
164
tok/s
6% VRAM
S
TinyLlama-1.1B1.1B
llama2K ctxchat
149
tok/s
7% VRAM
S
TinyLlama 1.1B1.1B
llama2K ctxchat
149
tok/s
7% VRAM
S
Llama-3.2-1B1.2B
llama4K ctxchat
137
tok/s
7% VRAM
S
LFM2.5-1.2B-Thinking1.2B
lfm122K ctxchatreasoningtool_use
137
tok/s
4% VRAM
S
DeepSeek Coder 1.3B1.3B
deepseek16K ctxcoding
126
tok/s
8% VRAM
S
OPT 1.3B1.3B
opt2K ctxchat
126
tok/s
7% VRAM
S
Phi-1 1.3B1.3B
phi2K ctxcoding
126
tok/s
8% VRAM
S
Phi-1.5 1.3B1.3B
phi2K ctxchatcoding
126
tok/s
8% VRAM
S
GPT-2 XL 1.5B1.5B
gpt21K ctxchat
109
tok/s
8% VRAM
S
Qwen2.5-Coder-1.5B1.5B
qwen32K ctxcodingchat
109
tok/s
8% VRAM
S
Qwen2 Math 1.5B1.5B
qwen4K ctxreasoning
109
tok/s
8% VRAM
S
Qwen 2.5 1.5B1.5B
qwen32K ctxchatcoding
109
tok/s
8% VRAM
S
Yi Coder 1.5B1.5B
yi125K ctxcoding
109
tok/s
8% VRAM
S
stablelm-2-1_6b1.6B
stablelm4K ctxchat
102
tok/s
9% VRAM
S
SmolLM2 1.7B1.71B
smollm8K ctxchat
96
tok/s
9% VRAM
S
Qwen3 1.7B1.7B
qwen32K ctxchatreasoning
96
tok/s
9% VRAM
S
Qwen 1.5 1.8B1.8B
qwen32K ctxchat
91
tok/s
9% VRAM
S
Moondream2 1.9B1.9B
other2K ctxvisionchat
86
tok/s
9% VRAM
S
Granite 4.0 Tiny7BMoE
granite125K ctxchatcodingmultilingual
82
tok/s
28% VRAM
S
Gemma 1 2B2B
gemma8K ctxchat
82
tok/s
10% VRAM
S
Granite 3.0 2B2B
granite128K ctxchatcoding
82
tok/s
10% VRAM
S
Granite 3.1 2B2B
granite128K ctxchatcoding
82
tok/s
10% VRAM
S
Qwen2-VL 2B2.21B
qwen32K ctxchatvision
74
tok/s
11% VRAM
S
Qwen3.5-2B2.3B
qwen256K ctxchat
71
tok/s
11% VRAM

Get personalized recommendations

See ranked models with benchmark scores, run commands, and precise speed estimates for your Data Center GPU Flex 170.

Find Models for Data Center GPU Flex 170Compare with other GPUs